diff --git a/include/net/dst.h b/include/net/dst.h index 0fb99a26e973..22aa93f165f1 100644 --- a/include/net/dst.h +++ b/include/net/dst.h @@ -109,7 +109,6 @@ u32 *dst_cow_metrics_generic(struct dst_entry *dst, unsigned long old); extern const u32 dst_default_metrics[]; #define DST_METRICS_READ_ONLY 0x1UL -#define DST_METRICS_FORCE_OVERWRITE 0x2UL #define DST_METRICS_FLAGS 0x3UL #define __DST_METRICS_PTR(Y) \ ((u32 *)((Y) & ~DST_METRICS_FLAGS)) @@ -120,11 +119,6 @@ static inline bool dst_metrics_read_only(const struct dst_entry *dst) return dst->_metrics & DST_METRICS_READ_ONLY; } -static inline void dst_metrics_set_force_overwrite(struct dst_entry *dst) -{ - dst->_metrics |= DST_METRICS_FORCE_OVERWRITE; -} - void __dst_destroy_metrics_generic(struct dst_entry *dst, unsigned long old); static inline void dst_destroy_metrics_generic(struct dst_entry *dst) diff --git a/include/net/ip6_fib.h b/include/net/ip6_fib.h index 20e80fa7bbdd..e00018011028 100644 --- a/include/net/ip6_fib.h +++ b/include/net/ip6_fib.h @@ -121,44 +121,14 @@ struct rt6_info { struct rt6key rt6i_prefsrc; struct inet6_dev *rt6i_idev; - unsigned long _rt6i_peer; u32 rt6i_metric; + u32 rt6i_pmtu; /* more non-fragment space at head required */ unsigned short rt6i_nfheader_len; u8 rt6i_protocol; }; -static inline struct inet_peer *rt6_peer_ptr(struct rt6_info *rt) -{ - return inetpeer_ptr(rt->_rt6i_peer); -} - -static inline bool rt6_has_peer(struct rt6_info *rt) -{ - return inetpeer_ptr_is_peer(rt->_rt6i_peer); -} - -static inline void __rt6_set_peer(struct rt6_info *rt, struct inet_peer *peer) -{ - __inetpeer_ptr_set_peer(&rt->_rt6i_peer, peer); -} - -static inline bool rt6_set_peer(struct rt6_info *rt, struct inet_peer *peer) -{ - return inetpeer_ptr_set_peer(&rt->_rt6i_peer, peer); -} - -static inline void rt6_init_peer(struct rt6_info *rt, struct inet_peer_base *base) -{ - inetpeer_init_ptr(&rt->_rt6i_peer, base); -} - -static inline void rt6_transfer_peer(struct rt6_info *rt, struct rt6_info *ort) -{ - inetpeer_transfer_peer(&rt->_rt6i_peer, &ort->_rt6i_peer); -} - static inline struct inet6_dev *ip6_dst_idev(struct dst_entry *dst) { return ((struct rt6_info *)dst)->rt6i_idev; @@ -189,15 +159,6 @@ static inline void rt6_update_expires(struct rt6_info *rt0, int timeout) rt0->rt6i_flags |= RTF_EXPIRES; } -static inline void rt6_set_from(struct rt6_info *rt, struct rt6_info *from) -{ - struct dst_entry *new = (struct dst_entry *) from; - - rt->rt6i_flags &= ~RTF_EXPIRES; - dst_hold(new); - rt->dst.from = new; -} - static inline void ip6_rt_put(struct rt6_info *rt) { /* dst_release() accepts a NULL parameter. diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 37b70e82bff8..21c2c818df3b 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -2121,6 +2121,8 @@ static struct rt6_info *addrconf_get_prefix_route(const struct in6_addr *pfx, fn = fib6_locate(&table->tb6_root, pfx, plen, NULL, 0); if (!fn) goto out; + + noflags |= RTF_CACHE; for (rt = fn->leaf; rt; rt = rt->dst.rt6_next) { if (rt->dst.dev->ifindex != dev->ifindex) continue; diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 5c48293ff062..352271154ddb 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -92,6 +92,7 @@ static void ip6_rt_update_pmtu(struct dst_entry *dst, struct sock *sk, struct sk_buff *skb, u32 mtu); static void rt6_do_redirect(struct dst_entry *dst, struct sock *sk, struct sk_buff *skb); +static void rt6_dst_from_metrics_check(struct rt6_info *rt); static int rt6_score_route(struct rt6_info *rt, int oif, int strict); #ifdef CONFIG_IPV6_ROUTE_INFO @@ -104,65 +105,14 @@ static struct rt6_info *rt6_get_route_info(struct net *net, const struct in6_addr *gwaddr, int ifindex); #endif -static void rt6_bind_peer(struct rt6_info *rt, int create) -{ - struct inet_peer_base *base; - struct inet_peer *peer; - - base = inetpeer_base_ptr(rt->_rt6i_peer); - if (!base) - return; - - peer = inet_getpeer_v6(base, &rt->rt6i_dst.addr, create); - if (peer) { - if (!rt6_set_peer(rt, peer)) - inet_putpeer(peer); - } -} - -static struct inet_peer *__rt6_get_peer(struct rt6_info *rt, int create) -{ - if (rt6_has_peer(rt)) - return rt6_peer_ptr(rt); - - rt6_bind_peer(rt, create); - return (rt6_has_peer(rt) ? rt6_peer_ptr(rt) : NULL); -} - -static struct inet_peer *rt6_get_peer_create(struct rt6_info *rt) -{ - return __rt6_get_peer(rt, 1); -} - static u32 *ipv6_cow_metrics(struct dst_entry *dst, unsigned long old) { - struct rt6_info *rt = (struct rt6_info *) dst; - struct inet_peer *peer; - u32 *p = NULL; + struct rt6_info *rt = (struct rt6_info *)dst; - if (!(rt->dst.flags & DST_HOST)) + if (rt->rt6i_flags & RTF_CACHE) + return NULL; + else return dst_cow_metrics_generic(dst, old); - - peer = rt6_get_peer_create(rt); - if (peer) { - u32 *old_p = __DST_METRICS_PTR(old); - unsigned long prev, new; - - p = peer->metrics; - if (inet_metrics_new(peer) || - (old & DST_METRICS_FORCE_OVERWRITE)) - memcpy(p, old_p, sizeof(u32) * RTAX_MAX); - - new = (unsigned long) p; - prev = cmpxchg(&dst->_metrics, old, new); - - if (prev != old) { - p = __DST_METRICS_PTR(prev); - if (prev & DST_METRICS_READ_ONLY) - p = NULL; - } - } - return p; } static inline const void *choose_neigh_daddr(struct rt6_info *rt, @@ -311,7 +261,6 @@ static inline struct rt6_info *ip6_dst_alloc(struct net *net, struct dst_entry *dst = &rt->dst; memset(dst + 1, 0, sizeof(*rt) - sizeof(*dst)); - rt6_init_peer(rt, table ? &table->tb6_peers : net->ipv6.peers); INIT_LIST_HEAD(&rt->rt6i_siblings); } return rt; @@ -323,8 +272,7 @@ static void ip6_dst_destroy(struct dst_entry *dst) struct inet6_dev *idev = rt->rt6i_idev; struct dst_entry *from = dst->from; - if (!(rt->dst.flags & DST_HOST)) - dst_destroy_metrics_generic(dst); + dst_destroy_metrics_generic(dst); if (idev) { rt->rt6i_idev = NULL; @@ -333,11 +281,6 @@ static void ip6_dst_destroy(struct dst_entry *dst) dst->from = NULL; dst_release(from); - - if (rt6_has_peer(rt)) { - struct inet_peer *peer = rt6_peer_ptr(rt); - inet_putpeer(peer); - } } static void ip6_dst_ifdown(struct dst_entry *dst, struct net_device *dev, @@ -652,15 +595,33 @@ static struct rt6_info *find_rr_leaf(struct fib6_node *fn, u32 metric, int oif, int strict, bool *do_rr) { - struct rt6_info *rt, *match; + struct rt6_info *rt, *match, *cont; int mpri = -1; match = NULL; - for (rt = rr_head; rt && rt->rt6i_metric == metric; - rt = rt->dst.rt6_next) + cont = NULL; + for (rt = rr_head; rt; rt = rt->dst.rt6_next) { + if (rt->rt6i_metric != metric) { + cont = rt; + break; + } + match = find_match(rt, oif, strict, &mpri, match, do_rr); - for (rt = fn->leaf; rt && rt != rr_head && rt->rt6i_metric == metric; - rt = rt->dst.rt6_next) + } + + for (rt = fn->leaf; rt && rt != rr_head; rt = rt->dst.rt6_next) { + if (rt->rt6i_metric != metric) { + cont = rt; + break; + } + + match = find_match(rt, oif, strict, &mpri, match, do_rr); + } + + if (match || !cont) + return match; + + for (rt = cont; rt; rt = rt->dst.rt6_next) match = find_match(rt, oif, strict, &mpri, match, do_rr); return match; @@ -959,7 +920,7 @@ redo_rt6_select: if (!(rt->rt6i_flags & (RTF_NONEXTHOP | RTF_GATEWAY))) nrt = rt6_alloc_cow(rt, &fl6->daddr, &fl6->saddr); - else if (!(rt->dst.flags & DST_HOST)) + else if (!(rt->dst.flags & DST_HOST) || !(rt->dst.flags & RTF_LOCAL)) nrt = rt6_alloc_clone(rt, &fl6->daddr); else goto out2; @@ -985,6 +946,7 @@ redo_rt6_select: goto redo_fib6_lookup_lock; out2: + rt6_dst_from_metrics_check(rt); rt->dst.lastuse = jiffies; rt->dst.__use++; @@ -1059,7 +1021,6 @@ struct dst_entry *ip6_blackhole_route(struct net *net, struct dst_entry *dst_ori new = &rt->dst; memset(new + 1, 0, sizeof(*rt) - sizeof(*new)); - rt6_init_peer(rt, net->ipv6.peers); new->__use = 1; new->input = dst_discard; @@ -1093,6 +1054,13 @@ struct dst_entry *ip6_blackhole_route(struct net *net, struct dst_entry *dst_ori * Destination cache support functions */ +static void rt6_dst_from_metrics_check(struct rt6_info *rt) +{ + if (rt->dst.from && + dst_metrics_ptr(&rt->dst) != dst_metrics_ptr(rt->dst.from)) + dst_init_metrics(&rt->dst, dst_metrics_ptr(rt->dst.from), true); +} + static struct dst_entry *ip6_dst_check(struct dst_entry *dst, u32 cookie) { struct rt6_info *rt; @@ -1109,6 +1077,8 @@ static struct dst_entry *ip6_dst_check(struct dst_entry *dst, u32 cookie) if (rt6_check_expired(rt)) return NULL; + rt6_dst_from_metrics_check(rt); + return dst; } @@ -1154,14 +1124,14 @@ static void ip6_rt_update_pmtu(struct dst_entry *dst, struct sock *sk, struct rt6_info *rt6 = (struct rt6_info *)dst; dst_confirm(dst); - if (mtu < dst_mtu(dst) && rt6->rt6i_dst.plen == 128) { + if (mtu < dst_mtu(dst) && (rt6->rt6i_flags & RTF_CACHE)) { struct net *net = dev_net(dst->dev); rt6->rt6i_flags |= RTF_MODIFIED; if (mtu < IPV6_MIN_MTU) mtu = IPV6_MIN_MTU; - dst_metric_set(dst, RTAX_MTU, mtu); + rt6->rt6i_pmtu = mtu; rt6_update_expires(rt6, net->ipv6.sysctl.ip6_rt_mtu_expires); } } @@ -1341,9 +1311,14 @@ static unsigned int ip6_default_advmss(const struct dst_entry *dst) static unsigned int ip6_mtu(const struct dst_entry *dst) { + const struct rt6_info *rt = (const struct rt6_info *)dst; + unsigned int mtu = rt->rt6i_pmtu; struct inet6_dev *idev; - unsigned int mtu = dst_metric_raw(dst, RTAX_MTU); + if (mtu) + goto out; + + mtu = dst_metric_raw(dst, RTAX_MTU); if (mtu) goto out; @@ -1590,10 +1565,8 @@ int ip6_route_add(struct fib6_config *cfg) ipv6_addr_prefix(&rt->rt6i_dst.addr, &cfg->fc_dst, cfg->fc_dst_len); rt->rt6i_dst.plen = cfg->fc_dst_len; - if (rt->rt6i_dst.plen == 128) { + if (rt->rt6i_dst.plen == 128) rt->dst.flags |= DST_HOST; - dst_metrics_set_force_overwrite(&rt->dst); - } #ifdef CONFIG_IPV6_SUBTREES ipv6_addr_prefix(&rt->rt6i_src.addr, &cfg->fc_src, cfg->fc_src_len); @@ -1785,6 +1758,9 @@ static int ip6_route_del(struct fib6_config *cfg) if (fn) { for (rt = fn->leaf; rt; rt = rt->dst.rt6_next) { + if ((rt->rt6i_flags & RTF_CACHE) && + !(cfg->fc_flags & RTF_CACHE)) + continue; if (cfg->fc_ifindex && (!rt->dst.dev || rt->dst.dev->ifindex != cfg->fc_ifindex)) @@ -1926,12 +1902,27 @@ out: * Misc support functions */ +static void rt6_set_from(struct rt6_info *rt, struct rt6_info *from) +{ + BUG_ON(from->dst.from); + + rt->rt6i_flags &= ~RTF_EXPIRES; + dst_hold(&from->dst); + rt->dst.from = &from->dst; + dst_init_metrics(&rt->dst, dst_metrics_ptr(&from->dst), true); +} + static struct rt6_info *ip6_rt_copy(struct rt6_info *ort, const struct in6_addr *dest) { struct net *net = dev_net(ort->dst.dev); - struct rt6_info *rt = ip6_dst_alloc(net, ort->dst.dev, 0, - ort->rt6i_table); + struct rt6_info *rt; + + if (ort->rt6i_flags & RTF_CACHE) + ort = (struct rt6_info *)ort->dst.from; + + rt = ip6_dst_alloc(net, ort->dst.dev, 0, + ort->rt6i_table); if (rt) { rt->dst.input = ort->dst.input; @@ -1940,7 +1931,6 @@ static struct rt6_info *ip6_rt_copy(struct rt6_info *ort, rt->rt6i_dst.addr = *dest; rt->rt6i_dst.plen = 128; - dst_copy_metrics(&rt->dst, &ort->dst); rt->dst.error = ort->dst.error; rt->rt6i_idev = ort->rt6i_idev; if (rt->rt6i_idev) @@ -2372,11 +2362,20 @@ static int rt6_mtu_change_route(struct rt6_info *rt, void *p_arg) PMTU discouvery. */ if (rt->dst.dev == arg->dev && - !dst_metric_locked(&rt->dst, RTAX_MTU) && - (dst_mtu(&rt->dst) >= arg->mtu || - (dst_mtu(&rt->dst) < arg->mtu && - dst_mtu(&rt->dst) == idev->cnf.mtu6))) { - dst_metric_set(&rt->dst, RTAX_MTU, arg->mtu); + !dst_metric_locked(&rt->dst, RTAX_MTU)) { + if (rt->rt6i_flags & RTF_CACHE) { + /* For RTF_CACHE with rt6i_pmtu == 0 + * (i.e. a redirected route), + * the metrics of its rt->dst.from has already + * been updated. + */ + if (rt->rt6i_pmtu && rt->rt6i_pmtu > arg->mtu) + rt->rt6i_pmtu = arg->mtu; + } else if (dst_mtu(&rt->dst) >= arg->mtu || + (dst_mtu(&rt->dst) < arg->mtu && + dst_mtu(&rt->dst) == idev->cnf.mtu6)) { + dst_metric_set(&rt->dst, RTAX_MTU, arg->mtu); + } } return 0; } @@ -2433,6 +2432,9 @@ static int rtm_to_fib6_config(struct sk_buff *skb, struct nlmsghdr *nlh, if (rtm->rtm_type == RTN_LOCAL) cfg->fc_flags |= RTF_LOCAL; + if (rtm->rtm_flags & RTM_F_CLONED) + cfg->fc_flags |= RTF_CACHE; + cfg->fc_nlinfo.portid = NETLINK_CB(skb).portid; cfg->fc_nlinfo.nlh = nlh; cfg->fc_nlinfo.nl_net = sock_net(skb->sk); @@ -2603,6 +2605,7 @@ static int rt6_fill_node(struct net *net, int iif, int type, u32 portid, u32 seq, int prefix, int nowait, unsigned int flags) { + u32 metrics[RTAX_MAX]; struct rtmsg *rtm; struct nlmsghdr *nlh; long expires; @@ -2716,7 +2719,10 @@ static int rt6_fill_node(struct net *net, goto nla_put_failure; } - if (rtnetlink_put_metrics(skb, dst_metrics_ptr(&rt->dst)) < 0) + memcpy(metrics, dst_metrics_ptr(&rt->dst), sizeof(metrics)); + if (rt->rt6i_pmtu) + metrics[RTAX_MTU - 1] = rt->rt6i_pmtu; + if (rtnetlink_put_metrics(skb, metrics) < 0) goto nla_put_failure; if (rt->rt6i_flags & RTF_GATEWAY) { diff --git a/net/ipv6/xfrm6_policy.c b/net/ipv6/xfrm6_policy.c index f337a908a76a..6ae256b4c55a 100644 --- a/net/ipv6/xfrm6_policy.c +++ b/net/ipv6/xfrm6_policy.c @@ -71,13 +71,6 @@ static int xfrm6_get_tos(const struct flowi *fl) return 0; } -static void xfrm6_init_dst(struct net *net, struct xfrm_dst *xdst) -{ - struct rt6_info *rt = (struct rt6_info *)xdst; - - rt6_init_peer(rt, net->ipv6.peers); -} - static int xfrm6_init_path(struct xfrm_dst *path, struct dst_entry *dst, int nfheader_len) { @@ -106,8 +99,6 @@ static int xfrm6_fill_dst(struct xfrm_dst *xdst, struct net_device *dev, return -ENODEV; } - rt6_transfer_peer(&xdst->u.rt6, rt); - /* Sheit... I remember I did this right. Apparently, * it was magically lost, so this code needs audit */ xdst->u.rt6.rt6i_flags = rt->rt6i_flags & (RTF_ANYCAST | @@ -255,10 +246,6 @@ static void xfrm6_dst_destroy(struct dst_entry *dst) if (likely(xdst->u.rt6.rt6i_idev)) in6_dev_put(xdst->u.rt6.rt6i_idev); dst_destroy_metrics_generic(dst); - if (rt6_has_peer(&xdst->u.rt6)) { - struct inet_peer *peer = rt6_peer_ptr(&xdst->u.rt6); - inet_putpeer(peer); - } xfrm_dst_destroy(xdst); } @@ -308,7 +295,6 @@ static struct xfrm_policy_afinfo xfrm6_policy_afinfo = { .get_saddr = xfrm6_get_saddr, .decode_session = _decode_session6, .get_tos = xfrm6_get_tos, - .init_dst = xfrm6_init_dst, .init_path = xfrm6_init_path, .fill_dst = xfrm6_fill_dst, .blackhole_route = ip6_blackhole_route,